{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:09:43Z","timestamp":1778789383635,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,10,5]],"date-time":"2016-10-05T00:00:00Z","timestamp":1475625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,10,5]]},"DOI":"10.1145\/2987550.2987554","type":"proceedings-article","created":{"date-parts":[[2016,9,21]],"date-time":"2016-09-21T12:42:53Z","timestamp":1474461773000},"page":"98-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":109,"title":["Addressing the straggler problem for iterative convergent parallel ML"],"prefix":"10.1145","author":[{"given":"Aaron","family":"Harlap","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henggang","family":"Cui","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Dai","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinliang","family":"Wei","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory R.","family":"Ganger","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phillip B.","family":"Gibbons","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Garth A.","family":"Gibson","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric P.","family":"Xing","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,10,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi M.","year":"2015","unstructured":"M. Abadi , A. Agarwal , P. Barham , E. Brevdo , Z. Chen , C. Citro , G. S. Corrado , A. Davis , J. Dean , M. Devin , TensorFlow: Large-scale machine learning on heterogeneous systems , 2015 . Software available from tensorflow.org. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442538"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124312"},{"key":"e_1_3_2_1_4_1","volume-title":"USENIX Annual Tech","author":"Albrecht J.","year":"2006","unstructured":"J. Albrecht , C. Tuttle , A. C. Snoeren , and A. Vahdat . Loose synchronization for large-scale networked systems . In USENIX Annual Tech , 2006 . J. Albrecht, C. Tuttle, A. C. Snoeren, and A. Vahdat. Loose synchronization for large-scale networked systems. In USENIX Annual Tech, 2006."},{"key":"e_1_3_2_1_5_1","first-page":"185","volume-title":"NSDI'13","author":"Ananthanarayanan G.","year":"2013","unstructured":"G. Ananthanarayanan , A. Ghodsi , S. Shenker , and I. Stoica . Effective straggler mitigation: Attack of the clones . In NSDI'13 , pages 185 -- 198 , 2013 . G. Ananthanarayanan, A. Ghodsi, S. Shenker, and I. Stoica. Effective straggler mitigation: Attack of the clones. In NSDI'13, pages 185--198, 2013."},{"key":"e_1_3_2_1_6_1","first-page":"1","volume-title":"Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10","author":"Ananthanarayanan G.","year":"2010","unstructured":"G. Ananthanarayanan , S. Kandula , A. Greenberg , I. Stoica , Y. Lu , B. Saha , and E. Harris . Reining in the outliers in map-reduce clusters using Mantri . In Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10 , pages 1 -- 16 . USENIX Association , 2010 . G. Ananthanarayanan, S. Kandula, A. Greenberg, I. Stoica, Y. Lu, B. Saha, and E. Harris. Reining in the outliers in map-reduce clusters using Mantri. In Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10, pages 1--16. USENIX Association, 2010."},{"key":"e_1_3_2_1_7_1","unstructured":"Apache Hadoop. http:\/\/hadoop.apache.org\/.  Apache Hadoop. http:\/\/hadoop.apache.org\/."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2006.311846"},{"key":"e_1_3_2_1_9_1","volume-title":"Pattern recognition and machine learning","author":"Bishop C. M.","year":"2006","unstructured":"C. M. Bishop Pattern recognition and machine learning , volume 4 . springer New York , 2006 . C. M. Bishop et al. Pattern recognition and machine learning, volume 4. springer New York, 2006."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/324133.324234"},{"key":"e_1_3_2_1_11_1","volume-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","author":"Chen T.","year":"2015","unstructured":"T. Chen , M. Li , Y. Li , M. Lin , N. Wang , M. Wang , T. Xiao , B. Xu , C. Zhang , and Z. Zhang . MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 , 2015 . T. Chen, M. Li, Y. Li, M. Lin, N. Wang, M. Wang, T. Xiao, B. Xu, C. Zhang, and Z. Zhang. MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274, 2015."},{"key":"e_1_3_2_1_12_1","first-page":"571","volume-title":"Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI'14","author":"Chilimbi T.","year":"2014","unstructured":"T. Chilimbi , Y. Suzue , J. Apacible , and K. Kalyanaraman . Project adam: Building an efficient and scalable deep learning training system . In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI'14 , pages 571 -- 582 . USENIX Association , 2014 . T. Chilimbi, Y. Suzue, J. Apacible, and K. Kalyanaraman. Project adam: Building an efficient and scalable deep learning training system. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI'14, pages 571--582. USENIX Association, 2014."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2490483.2490505"},{"key":"e_1_3_2_1_14_1","first-page":"37","volume-title":"USENIX ATC","author":"Cui H.","year":"2014","unstructured":"H. Cui , J. Cipar , Q. Ho , J. K. Kim , S. Lee , A. Kumar , J. Wei , W. Dai , G. R. Ganger , P. B. Gibbons , G. A. Gibson , and E. P. Xing . Exploiting bounded staleness to speed up big data analytics . In USENIX ATC , pages 37 -- 48 , 2014 . H. Cui, J. Cipar, Q. Ho, J. K. Kim, S. Lee, A. Kumar, J. Wei, W. Dai, G. R. Ganger, P. B. Gibbons, G. A. Gibson, and E. P. Xing. Exploiting bounded staleness to speed up big data analytics. In USENIX ATC, pages 37--48, 2014."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670984"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670981"},{"key":"e_1_3_2_1_18_1","volume-title":"Berkeley AMPLab Cloud Seminar","author":"Dean J.","year":"2012","unstructured":"J. Dean . Achieving rapid response times in large online services . In Berkeley AMPLab Cloud Seminar , 2012 . J. Dean. Achieving rapid response times in large online services. In Berkeley AMPLab Cloud Seminar, 2012."},{"key":"e_1_3_2_1_19_1","volume-title":"OSDI","author":"Dean J.","year":"2004","unstructured":"J. Dean and S. Ghemawat . Mapreduce: Simplified data processing on large clusters . In OSDI , 2004 . J. Dean and S. Ghemawat. Mapreduce: Simplified data processing on large clusters. In OSDI, 2004."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654113"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370581"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168847"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.41"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020426"},{"key":"e_1_3_2_1_25_1","volume-title":"PRObE: A thousand-node experimental cluster for computer systems research. USENIX","author":"Gibson G.","year":"2013","unstructured":"G. Gibson , G. Grider , A. Jacobson , and W. Lloyd . PRObE: A thousand-node experimental cluster for computer systems research. USENIX ; login, 38(3), 2013 . G. Gibson, G. Grider, A. Jacobson, and W. Lloyd. PRObE: A thousand-node experimental cluster for computer systems research. USENIX; login, 38(3), 2013."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. OSDI","author":"Gonzalez J. E.","year":"2012","unstructured":"J. E. Gonzalez , Y. Low , H. Gu , D. Bickson , and C. Guestrin . Powergraph: Distributed graph-parallel computation on natural graphs . In Proc. OSDI , 2012 . J. E. Gonzalez, Y. Low, H. Gu, D. Bickson, and C. Guestrin. Powergraph: Distributed graph-parallel computation on natural graphs. In Proc. OSDI, 2012."},{"key":"e_1_3_2_1_27_1","first-page":"599","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Gonzalez J. E.","year":"2014","unstructured":"J. E. Gonzalez , R. S. Xin , A. Dave , D. Crankshaw , M. J. Franklin , and I. Stoica . GraphX: Graph processing in a distributed dataflow framework . In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14) , pages 599 -- 613 , 2014 . J. E. Gonzalez, R. S. Xin, A. Dave, D. Crankshaw, M. J. Franklin, and I. Stoica. GraphX: Graph processing in a distributed dataflow framework. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14), pages 599--613, 2014."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0307752101"},{"key":"e_1_3_2_1_29_1","volume-title":"Tier ml: Using tiers of reliability for agile elasticity in machine learning","author":"Harlap A.","year":"2016","unstructured":"A. Harlap , G. R. Ganger , and P. B. Gibbons . Tier ml: Using tiers of reliability for agile elasticity in machine learning . 2016 . A. Harlap, G. R. Ganger, and P. B. Gibbons. Tier ml: Using tiers of reliability for agile elasticity in machine learning. 2016."},{"key":"e_1_3_2_1_30_1","first-page":"22","volume-title":"NSDI","volume":"11","author":"Hindman B.","year":"2011","unstructured":"B. Hindman , A. Konwinski , M. Zaharia , A. Ghodsi , A. D. Joseph , R. H. Katz , S. Shenker , and I. Stoica . Mesos: A platform for fine-grained resource sharing in the data center . In NSDI , volume 11 , pages 22 -- 22 , 2011 . B. Hindman, A. Konwinski, M. Zaharia, A. Ghodsi, A. D. Joseph, R. H. Katz, S. Shenker, and I. Stoica. Mesos: A platform for fine-grained resource sharing in the data center. In NSDI, volume 11, pages 22--22, 2011."},{"key":"e_1_3_2_1_31_1","volume-title":"NIPS","author":"Ho Q.","year":"2013","unstructured":"Q. Ho , J. Cipar , H. Cui , S. Lee , J. K. Kim , P. B. Gibbons , G. A. Gibson , G. R. Ganger , and E. P. Xing . More effective distributed ML via a Stale Synchronous Parallel parameter server . In NIPS , 2013 . Q. Ho, J. Cipar, H. Cui, S. Lee, J. K. Kim, P. B. Gibbons, G. A. Gibson, G. R. Ganger, and E. P. Xing. More effective distributed ML via a Stale Synchronous Parallel parameter server. In NIPS, 2013."},{"key":"e_1_3_2_1_32_1","volume-title":"USENIX conference on Hot topics in operating systems (HotOS)","author":"Krevat E.","year":"2011","unstructured":"E. Krevat , J. Tucek , and G. R. Ganger . Disks are like snowflakes: no two are alike . In USENIX conference on Hot topics in operating systems (HotOS) , 2011 . E. Krevat, J. Tucek, and G. R. Ganger. Disks are like snowflakes: no two are alike. In USENIX conference on Hot topics in operating systems (HotOS), 2011."},{"key":"e_1_3_2_1_33_1","first-page":"1097","volume-title":"Advances in neural information processing systems","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. E. Hinton . Imagenet classification with deep convolutional neural networks . In Advances in neural information processing systems , pages 1097 -- 1105 , 2012 . A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097--1105, 2012."},{"key":"e_1_3_2_1_34_1","volume-title":"NIPS","author":"Langford J.","year":"2009","unstructured":"J. Langford , A. J. Smola , and M. Zinkevich . Slow learners are fast . In NIPS , 2009 . J. Langford, A. J. Smola, and M. Zinkevich. Slow learners are fast. In NIPS, 2009."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"e_1_3_2_1_36_1","first-page":"19","volume-title":"NIPS","author":"Li M.","year":"2014","unstructured":"M. Li , D. G. Andersen , A. J. Smola , and K. Yu . Communication efficient distributed machine learning with the parameter server . In NIPS , pages 19 -- 27 , 2014 . M. Li, D. G. Andersen, A. J. Smola, and K. Yu. Communication efficient distributed machine learning with the parameter server. In NIPS, pages 19--27, 2014."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557082"},{"key":"e_1_3_2_1_38_1","volume-title":"Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Low Y.","year":"2010","unstructured":"Y. Low , J. Gonzalez , A. Kyrola , D. Bickson , C. Guestrin , and J. M. Hellerstein . GraphLab: A new parallel framework for machine learning . In Conference on Uncertainty in Artificial Intelligence (UAI) , 2010 . Y. Low, J. Gonzalez, A. Kyrola, D. Bickson, C. Guestrin, and J. M. Hellerstein. GraphLab: A new parallel framework for machine learning. In Conference on Uncertainty in Artificial Intelligence (UAI), 2010."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522738"},{"key":"e_1_3_2_1_41_1","unstructured":"New York Times dataset. http:\/\/www.ldc.upenn.edu\/.  New York Times dataset. http:\/\/www.ldc.upenn.edu\/."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050204"},{"key":"e_1_3_2_1_43_1","first-page":"1","volume-title":"Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10","author":"Power R.","year":"2010","unstructured":"R. Power and J. Li . Piccolo: building fast, distributed programs with partitioned tables . In Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10 , pages 1 -- 14 . USENIX Association , 2010 . R. Power and J. Li. Piccolo: building fast, distributed programs with partitioned tables. In Proceedings of the 9th USENIX conference on Operating systems design and implementation, OSDI'10, pages 1--14. USENIX Association, 2010."},{"key":"e_1_3_2_1_44_1","unstructured":"Power-law distribution. http:\/\/en.wikipedia.org\/wiki\/Power_law.  Power-law distribution. http:\/\/en.wikipedia.org\/wiki\/Power_law."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"e_1_3_2_1_46_1","first-page":"329","volume-title":"Middleware","author":"Rowstron A.","year":"2001","unstructured":"A. Rowstron and P. Druschel . Pastry: Scalable, decentralized object location, and routing for large-scale peer-to-peer systems . In Middleware 2001 , pages 329 -- 350 . Springer , 2001. A. Rowstron and P. Druschel. Pastry: Scalable, decentralized object location, and routing for large-scale peer-to-peer systems. In Middleware 2001, pages 329--350. Springer, 2001."},{"key":"e_1_3_2_1_47_1","volume-title":"ImageNet Large Scale Visual Recognition Challenge","author":"Russakovsky O.","year":"2014","unstructured":"O. Russakovsky , J. Deng , H. Su , J. Krause , S. Satheesh , S. Ma , Z. Huang , A. Karpathy , A. Khosla , M. Bernstein , A. C. Berg , and L. Fei-Fei . ImageNet Large Scale Visual Recognition Challenge , 2014 . O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei. ImageNet Large Scale Visual Recognition Challenge, 2014."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/964723.383071"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391254"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"e_1_3_2_1_51_1","first-page":"10","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"Zaharia M.","year":"2010","unstructured":"M. Zaharia , M. Chowdhury , M. J. Franklin , S. Shenker , and I. Stoica . Spark: Cluster computing with working sets . HotCloud , 10 : 10 -- 10 , 2010 . M. Zaharia, M. Chowdhury, M. J. Franklin, S. Shenker, and I. Stoica. Spark: Cluster computing with working sets. HotCloud, 10:10--10, 2010.","journal-title":"HotCloud"},{"key":"e_1_3_2_1_52_1","volume-title":"OSDI","author":"Zaharia M.","year":"2008","unstructured":"M. Zaharia , A. Konwinski , A. D. Joseph , R. H. Katz , and I. Stoica . Improving MapReduce performance in heterogeneous environments . In OSDI , 2008 . M. Zaharia, A. Konwinski, A. D. Joseph, R. H. Katz, and I. Stoica. Improving MapReduce performance in heterogeneous environments. In OSDI, 2008."}],"event":{"name":"SoCC '16: ACM Symposium on Cloud Computing","location":"Santa Clara CA USA","acronym":"SoCC '16","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Seventh ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2987550.2987554","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2987550.2987554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:40:06Z","timestamp":1750218006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2987550.2987554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,5]]},"references-count":52,"alternative-id":["10.1145\/2987550.2987554","10.1145\/2987550"],"URL":"https:\/\/doi.org\/10.1145\/2987550.2987554","relation":{},"subject":[],"published":{"date-parts":[[2016,10,5]]},"assertion":[{"value":"2016-10-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}